OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
View on GitHub →PythonApache-2.0llmslorareinforcement-learningagentagentic-ai
Stars
10.5k
Δ 7d
+105
Δ 30d
+513
Age
1 yr
Last push
2h ago
90-day star history
Most-wanted open issues
Ranked by 👍 reactions. 63 open issues total, checked 2026-07-17.
| Issue | 👍 | Comments | Opened |
|---|---|---|---|
| 3 | 4 | 1 yr | |
Add support for SFT through ART directly enhancement | 3 | 1 | 11 mo |
Feature: Dr. GRPO Support enhancement | 3 | 1 | 10 mo |
| 3 | 1 | 11 mo | |
| 3 | 3 | 7 mo |
Alternatives in Agent SDKs & frameworks
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory a…
⭐46.0k
Python
3 yrs
Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gem…
⭐38.0k
+2257d
Python
11 mo
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI P…
⭐36.1k
+1947d
TypeScript
3 yrs
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to…
⭐29.3k
+1107d
TypeScript
2 yrs